pdf_title_image/parse_index_table.py

from typing import List

import pandas as pd

# from celery_tasks import app

# @app.task
def parse_index_table(tables_list: List[dict]):
    for table_dict in tables_list:
        if (table_dict.get('table_name') == '索引表') or ('索引表' in table_dict.get('table')[0][0]):
            # return True
            table = table_dict.get('table')
            df = pd.DataFrame(table[2:], columns=table[1])
            print(df[['条款号', '评分因素', '页码']])
    # return False


if __name__ == '__main__':
    import json
    from glob import glob
    for file in glob('D:\\desktop\\三峡水利\\data\\projects\\*\\投标\\*\\*table.json'):
    # with open('D:\\desktop\\三峡水利\\data\\projects\\三峡左岸及地下电站地坪整治\\投标\\湖北建新建设工程有限公司_T221100130348%2F01整本文件\\投标文件-修改版9-5-1-1-table.json', 'r', encoding='utf-8') as fp:
        print(file)
        with open(file, 'r', encoding='utf-8') as fp:
            tables_list = json.load(fp)
        print(parse_index_table(tables_list=tables_list))